计算机应用与软件2017，Vol.34Issue(6)：257-261,5.DOI:10.3969/j.issn.1000-386x.2017.06.046
未知状态模型下基于高阶容积卡尔曼滤波和神经网络的状态估计算法
STATE ESTIMATION ALGORITHM BASED ON HIGH ORDER CUBATURE KALMAN FILTER AND NEURAL NETWORK WITH UNKNOWN STATE MODEL
摘要
Abstract
In view of the nonlinear state model of the system is unknown, this paper presents a state estimation algorithm based on high order cubature Kalman filter and neural network to solve the problem of state estimation of unknown nonlinear system model.The neural network is used to establish the state space model for the nonlinear system.Then, the weight of the neural network and the state of the system variables together are combines as the new state variables.And the new state is updated in real time by high order cubature Kalman filter, so as to achieve the neural network on the nonlinear system model of the real approximation and accurate estimation of the state value.The final target tracking simulation shows that the algorithm has higher estimation accuracy.关键词
非线性系统/未知模型/高阶容积卡尔曼滤波/神经网络Key words
Nonlinear system/Unknown model/High order cubature/Kalman filter/Neural network分类
信息技术与安全科学引用本文复制引用
许大星,王海伦..未知状态模型下基于高阶容积卡尔曼滤波和神经网络的状态估计算法[J].计算机应用与软件,2017,34(6):257-261,5.基金项目
国家自然科学基金项目(61403229) （61403229）
浙江省科技厅公益项目(2015C33230). （2015C33230）
